jddbucknole / Awesome-Data-Science-Materials

Summary of some data science materials

Awesome-Data-Science-Materials

This repository contains a summary of some data science materials: papers, useful packages, MOOC, career development info, etc.

Data Science Education & Career

• Machine Learning Mastery: Less math and more tutorials with working code.
• Deep Learning: Deep Learning Specialization. It teaches the most important and foundational principles of Deep Learning
• Introduction to Deep Learning (MIT): It is a high-level introduction course. If you want to learn more details about the building blocks of deep learning, refer to the previous course from deeplearning.ai
• TensorFlow in Practice: This Specialization will teach you best practices for using TensorFlow. It is code heavy but doesn't introduce the theoretical background of the models. It is a great companion to Deep Learning Specialization.

Data Science Paper

• Practical Data Science for Stats - a PeerJ Collection: Very interesting and insightful papers on data science practice

SQL

https://www.w3schools.com/sql/

1. SQL for Data Scientist Learning Notes: http://scientistcafe.com/notes/SQL
2. Select * SQL: https://selectstarsql.com/
3. Leetcode: https://lnkd.in/g3c5JGC
4. LinkedIn Learning: https://lnkd.in/gQXFc4n
5. Window Functions: https://lnkd.in/g3RtPCJ
6. HackerRank: https://lnkd.in/grv_9sB
7. W3 Schools: https://lnkd.in/gJPfrrv
8. CodeAcademy: https://lnkd.in/gT5xmpN
9. SQLZoo: https://sqlzoo.net/
10. SQL Bolt: https://sqlbolt.com/
11. 1. Zachary Thomas' SQL Questions https://lnkd.in/g-JJzuD
12. Effective SQL for Data Science https://ploomber.io/posts/sql/

Deep Learning

Effective CNNs

• LeNet -5: LeCun et al., 1998. Gradient-based learning applied to document recognition

• AlexNet: Krizhevsky et al., 2012. ImageNet Classification with Deep Convolutional Neural Networks

• VGG-16: Simonyan & Zisserman 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition

• ResNets: He et al., 2015. Deep Residual Learning for Image Recognition

Different Architecture Search Algorithms:

• NASnet: 1800 GPU days (5 yrs on 1 GPU)

• AmoebaNet: 3150 GPU days

• DARTS: 4 GPU days

• ENAS: 1000 x cheaper than standard NAS

Understanding Neural Networks

• Understanding Neural Networks Through Deep Visualization, Video

• Deep Neural Networks are Easily Fooled

RNN

• Cho et al., 2014. On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
• Chung et al., 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Hochreiter & Schmidhuber 1997. Long short-term memory

Others

• Most Cited Deep Learning Papers: A curated list of the most cited deep learning papers (since 2012)
• Image Kernels: http://setosa.io/ev/image-kernels/
• http://www.fast.ai

Natural Language Processing

• cleanNLP: cleanNLP calls one of two state of the art NLP libraries (CoreNLP or spaCy). The package currently supports input text in English, German, French, and Spanish.
• spaCy
• Dan Jurafsky & Chris Manning: Natural Language Processing: https://www.youtube.com/playlist?list=PL6397E4B26D00A269

Experimentation

• 'pwr' package: https://cran.r-project.org/web/packages/pwr/vignettes/pwr-vignette.html

Tidy Data

• broom package: takes the messy output of built-in functions in R, such as lm, nls, or t.test, and turns them into tidy data frames

Causal Inference

• CausalTree

Others

• Unix Learning Notes: http://scientistcafe.com/notes/Unix/
• scijava-jupyter-kernel aims to be a polyglot Jupyter kernel. It uses the Scijava scripting languages to execute the code in Jupyter client and it's possible to use different languages in the same notebook.

Some of the supported languages are Groovy (default), Python, Beanshell, Clojure, Java, Javascript, Ruby and Scala.

https://github.com/scijava/scijava-jupyter-kernel/tree/afd8c1c7be5b92a734e0fac9d78bcc0216162340

• RStudio Conference 2018

  • "Official" collection of presentations https://github.com/rstudio/rstudio-conf/tree/master/2018
  • Slides: https://github.com/simecek/RStudioConf2018Slides
  • Training courses: https://www.dropbox.com/sh/8t4k8lgk0su3gjb/AAA6M50Iw_-6T1EEcrzV49pUa?dl=0

• plumber: https://www.rplumber.io/docs/

Reproducible Report

R Markdown Theme Gallery: http://www.datadreaming.org/post/r-markdown-theme-gallery/

Web Development

• Giraffe Academy (fun and free online programming education): http://www.giraffeacademy.com
• JavaScript Online Editor:
  • https://jsfiddle.net
  • https://codepen.io
• HTML
  • WHATWG: Web Hypertext Application Technology Group
  • W3C: World Wide Web Consortium
  • Resources for validating html:
    • html5 standard (academic type of reading). If you want to kind of know what the actual standard is that everybody agreed to, this is a great document to start with.: https://www.w3.org/TR/html5/
    • The site keeps track of HTML5, SVG, CSS standards, JavaScript APIs etc. It tells you which browser supports what: https://caniuse.com
    • Find out whether or not your HTML actually is going to work in browsers: http://validator.w3.org/#validate_by_url
    • Check browser statistics: https://www.w3schools.com/browsers/default.asp